dotnet · gewarren · Aug 19, 2025 · Aug 19, 2025
@@ -46,7 +46,7 @@ For example, given the user input *Give me three ideas for a healthy breakfast i
 
 Some generative AI applications produce image outputs from natural language inputs. Depending on the application and its models, users might be able to specify:
 
-- The people or things to appear the image
+- The people or things to appear in the image
 - The artistic style to create the image in
 - References for generating similar images
 

@@ -51,7 +51,7 @@ The Kernel builds the `tools` parameter of a request based on your decorators, o
 
 ## Token counts
 
-Function descriptions are include in the system message of your request to a model. These function descriptions count against your model's [token limit](/azure/ai-services/openai/quotas-limits) and are [included in the cost of the request](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/).
+Function descriptions are included in the system message of your request to a model. These function descriptions count against your model's [token limit](/azure/ai-services/openai/quotas-limits) and are [included in the cost of the request](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/).
 
 If your request exceeds the model's token limit, try the following modifications:
 

@@ -34,7 +34,7 @@ Vector databases and their search features are especially useful in [RAG pattern
 1. Store and index the embeddings in a vector database or search service.
 1. Convert user prompts from your application to embeddings.
 1. Run a vector search across your data, comparing the user prompt embedding to the embeddings your database.
-1. Use a language model such as GPT-35 or GPT-4 to assembly a user friendly completion from the vector search results.
+1. Use a language model such as GPT-35 or GPT-4 to assemble a user friendly completion from the vector search results.
 
 Visit the [Implement Azure OpenAI with RAG using vector search in a .NET app](../tutorials/tutorial-ai-vector-search.md) tutorial for a hands-on example of this flow.
 

@@ -32,7 +32,7 @@ Intent:
 
 There are two primary use cases for zero-shot learning:
 
-- **Work with fined-tuned LLMs** - Because it relies on the model's existing knowledge, zero-shot learning is not as resource-intensive as few-shot learning, and it works well with LLMs that have already been fined-tuned on instruction datasets. You might be able to rely solely on zero-shot learning and keep costs relatively low.
+- **Work with fined-tuned LLMs** - Because it relies on the model's existing knowledge, zero-shot learning is not as resource-intensive as few-shot learning, and it works well with LLMs that have already been fine-tuned on instruction datasets. You might be able to rely solely on zero-shot learning and keep costs relatively low.
 - **Establish performance baselines** - Zero-shot learning can help you simulate how your app would perform for actual users. This lets you evaluate various aspects of your model's current performance, such as accuracy or precision. In this case, you typically use zero-shot learning to establish a performance baseline and then experiment with few-shot learning to improve performance.
 
 ## Few-shot learning

@@ -68,7 +68,7 @@ dotnet add package ModelContextProtocol --prerelease
 
 Instead of building unique connectors for each integration point, you can often leverage or reference prebuilt integrations from various providers such as GitHub and Docker:
 
-- [Available MPC clients](https://modelcontextprotocol.io/clients)
+- [Available MCP clients](https://modelcontextprotocol.io/clients)
 - [Available MCP servers](https://modelcontextprotocol.io/examples)
 
 ### Integration with Microsoft.Extensions.AI

@@ -146,7 +146,7 @@ As with other `IChatClient` implementations, the `RateLimitingChatClient` can be
 
 :::code language="csharp" source="snippets/microsoft-extensions-ai/ConsoleAI.CustomClientMiddle/Program.cs":::
 
-To simplify the composition of such components with others, component authors should create a `Use*` extension method for registering the component into a pipeline. For example, consider the following `UseRatingLimiting` extension method:
+To simplify the composition of such components with others, component authors should create a `Use*` extension method for registering the component into a pipeline. For example, consider the following `UseRateLimiting` extension method:
 
 :::code language="csharp" source="snippets/microsoft-extensions-ai/AI.Shared/RateLimitingChatClientExtensions.cs" id="one":::
 

@@ -25,7 +25,7 @@ Millions of developers use .NET to create applications that run on the web, on m
 The opportunities with AI are near endless. Here are a few examples of solutions you can build using AI in your .NET applications:
 
 * Language processing: Create virtual agents or chatbots to talk with your data and generate content and images.
-* Computer vision: Identify objects in an object or video.
+* Computer vision: Identify objects in an image or video.
 * Audio generation: Use synthesized voices to interact with customers.
 * Classification: Label the severity of a customer-reported issue.
 * Task automation: Automatically perform the next step in a workflow as tasks are completed.